09:01
Running a 27B model at 130 tokens sec on a single GPU Locally with Luce DFlash
LlamaDeFlash is a custom inference engine built from scratch in C++ and CUDA — no vLLM, no llama.cpp, no Python in the critical path...
Sort by: Newest Items
There are 14 items in this page
10:01
The Hidden Engine Behind DeepSeek V4 – DeepEP V2 and TileKernels Explained
While most coverage of DeepSeek V4 focuses on benchmark scores, Fahd Mirza goes a level deeper to explain the two open-sourced infras...
10:33
Kimi FlashKDA: 2x Faster AI Prefill — Installed, Explained and Tested Locally
Fahd Mirza walks through the live installation of Flash KDA, Moonshot AI's open-source CUDA kernel that accelerates the prefill phase...
01:43:13
Jensen Huang – TPU competition, why we should sell chips to China, & Nvidia’s supply chain moat
Dwarkesh Patel sits down with Nvidia CEO Jensen Huang for one of the most substantive interviews the company's founder has given on N...
16:23
3 Steps to Train Perfect LTX 2.3 Video LoRAs|How to Train Custom LTX 2.3 LoRAs (Video + Audio!)
Veteran AI presents a detailed three-part guide to training custom character LoRAs for LTX Video 2.3, covering dataset preparation, t...
01:06:06
Jensen Huang: Nvidia’s Future, Physical AI, Rise of the Agent, Inference Explosion, AI PR Crisis
In a sit-down interview at Nvidia's GTC conference, CEO Jensen Huang joined the All-In Podcast to explain the company's strategic tra...
14:00
I Coded an AI Waifu that Controls My PC (Claude Cowork + ThreeJS)
Alpha Stack walks through building 'Claudina,' a 3D animated desktop companion that integrates with Claude Code's MCP server to give...
12:15
Voicebox: Free ElevenLabs Alternative – Runs Locally on Windows CPU
Fahd Mirza installs and stress-tests Voicebox, a free open-source voice cloning and text-to-speech application, on a CPU-only Windows...
01:24:45
Forward Future Live | 02.06.26 | Guests from Modular, Emergence Capital, & Axiom
This episode of Forward Future Live brings together Matthew Berman, co-host Nick Wentz, and three guests to break down the biggest AI...
13:28
Voice Cloning is Dead? Welcome to AI “Voice Design” (Qwen3 TTS)|Qwen3 TTS Full Tutorial
Qwen3 TTS goes beyond traditional voice cloning to offer a three-function voice synthesis platform: voice design (generating voices f...